TA6a2.2

Learning Safety Critics via a Non-Contractive Binary Bellman Operator

Agustin Castellano, Johns Hopkins University, United States; Hancheng Min, University of Pennsylvania, United States; Juan Andrés Bazerque, University of Pittsburgh, United States; Enrique Mallada, Johns Hopkins University, United States
Session:
TA6a2: Learning with Constraints (Invited) Poster
Track:
Adaptive Systems, Machine Learning, Data Analytics
Location:
Kiln
Presentation Time:
Tue, 31 Oct, 08:15 - 09:55 PT (UTC -8)
Session Chair:
Santiago Paternain, Rensselaer Polytechnic Institute
Presentation
Discussion
Resources
No resources available.
Session TA6a2
TA6a2.1: Learning Non-myopic Power Allocation in Constrained Scenarios
Arindam Chowdhury, Rice University, United States; Santiago Paternain, Rensselaer Polytechnic Institute, United States; Gunjan Verma, Ananthram Swami, DEVCOM Army Research Laboratory, United States; Santiago Segarra, Rice University, United States
TA6a2.2: Learning Safety Critics via a Non-Contractive Binary Bellman Operator
Agustin Castellano, Johns Hopkins University, United States; Hancheng Min, University of Pennsylvania, United States; Juan Andrés Bazerque, University of Pittsburgh, United States; Enrique Mallada, Johns Hopkins University, United States
TA6a2.3: Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance
Lisha Chen, Heshan Fernando, Rensselaer Polytechnic Institute, United States; Yiming Ying, State University of New York at Albany, United States; Tianyi Chen, Rensselaer Polytechnic Institute, United States
Contacts